Instructions to use LLM360/AmberSafe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM360/AmberSafe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM360/AmberSafe")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LLM360/AmberSafe") model = AutoModelForCausalLM.from_pretrained("LLM360/AmberSafe") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LLM360/AmberSafe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM360/AmberSafe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/AmberSafe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM360/AmberSafe
- SGLang
How to use LLM360/AmberSafe with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "LLM360/AmberSafe" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/AmberSafe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "LLM360/AmberSafe" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/AmberSafe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM360/AmberSafe with Docker Model Runner:
docker model run hf.co/LLM360/AmberSafe
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,7 @@ We present AmberSafe, a safety-finetuned instruction model using [LLM360/AmberCh
|
|
| 44 |
- **Resources for more information:**
|
| 45 |
- [Metrics](https://github.com/LLM360/Analysis360)
|
| 46 |
- [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
# Loading AmberSafe
|
|
|
|
| 44 |
- **Resources for more information:**
|
| 45 |
- [Metrics](https://github.com/LLM360/Analysis360)
|
| 46 |
- [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
|
| 47 |
+
- [Finetuning Code](https://github.com/LLM360/amber-train/tree/main/finetune/ambersafe)
|
| 48 |
|
| 49 |
|
| 50 |
# Loading AmberSafe
|